Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43459
    Prev
    Next
    INDEX
    Explanations

    scale

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    掉
    -0.07
    områ
    -0.07
    �
    -0.07
    nissen
    -0.07
    412
    -0.07
    shadow
    -0.07
    cta
    -0.07
     Cher
    -0.07
    obby
    -0.07
    स्थित
    -0.07
    POSITIVE LOGITS
     ache
    0.08
     Yan
    0.08
     Augustine
    0.07
     CENT
    0.07
    ிரி
    0.07
    eless
    0.07
    Brad
    0.07
     Ba
    0.07
     kohal
    0.07
     Ingrid
    0.07
    Activations Density 0.007%

    No Known Activations